© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10064
    Prev
    Next
    INDEX
    Explanations

    Special compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ļ个æĹ¶ä»£
    -0.10
    大åŁİå¸Ĥ
    -0.09
    hammad
    -0.09
    æĥ®
    -0.09
    mith
    -0.09
     Strap
    -0.08
    æĺ¥å¤ı
    -0.08
    å¸Ĥä¸Ńå¿ĥ
    -0.08
    íijľ
    -0.08
     Gibson
    -0.08
    POSITIVE LOGITS
    éħįå¥Ĺ
    0.09
    ities
    0.09
    è´¨éĩıéĹ®é¢ĺ
    0.08
    æĨ¨
    0.08
    -interest
    0.08
    izations
    0.08
    æĤª
    0.08
    ought
    0.08
    Needs
    0.08
    stit
    0.08
    Activations Density 0.017%

    No Known Activations